© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 5120
    Prev
    Next
    INDEX
    Explanations

    interactions involving hugging and physical affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lon
    -0.17
    orny
    -0.17
     Consumption
    -0.15
    upo
    -0.15
    acz
    -0.14
    autiful
    -0.14
    kah
    -0.14
    ddit
    -0.14
    eyed
    -0.14
    horn
    -0.14
    POSITIVE LOGITS
     atlas
    0.14
    liÄŁine
    0.14
     Gio
    0.14
    æĤ
    0.14
    .fig
    0.14
    Äįka
    0.14
     pressing
    0.13
     Seb
    0.13
    atable
    0.13
    Statics
    0.13
    Activations Density 0.108%

    No Known Activations